JP2000231558A - Communication equipment, communicating method and recording medium with communication control program recorded thereon - Google Patents

Abstract

PROBLEM TO BE SOLVED: To represent intonation and feelings expression of speech and also to meet the timing of communication. SOLUTION: A machine translation circuit 12 translates a voice language recognized by a voice recognition circuit 11 into another language such as can be caught by a user B. A voice synthetic circuit 13 converts the other translated language into voice and supplies it to a voice translation control part 15. The circuit 15 reads voice stored in a speech buffer 14 at prescribed timing, arranges this voice of a user A and the translated voice in a prescribed order and transmits these voices to the user B.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a communication device having a speech translation function, a communication method, and a recording medium on which a communication control program is recorded.

[0002]

2. Description of the Related Art Today, with the development of speech recognition technology, machine translation technology, and text-to-speech synthesis technology, speech translation can be automatically performed. By incorporating such technology into a communication device such as a telephone, a function such as a speech translation telephone is realized.

[0003] For example, a speech translation telephone converts speech spoken by a user into a sentence by a speech recognition function, converts the sentence into another language by machine translation, and translates the translation result into a speech in another language through a speech synthesizer. To play as.

[0004]

SUMMARY OF THE INVENTION However, speech recognition and
Although the machine translation process can correctly convey the meaning to some extent, it is very difficult to recognize the intonation of the utterance, the emotional expression included in the utterance, and reflect the result in the translation result.

[0005] Further, due to the time overhead required for speech translation, the timing until the uttered content of one user is transmitted to the other user is not known, resulting in a shift in communication timing.

The present invention has been proposed in view of such circumstances, and a communication apparatus, a communication method, and a communication method capable of expressing the intonation or emotional expression of an utterance in a translation result and adjusting the timing of communication. An object is to provide a recording medium on which a control program is recorded.

[0007]

In order to solve the above-mentioned problems, a communication device according to the present invention comprises: a voice recognition unit for recognizing a voice of a speaker input in a first language; Machine translation means for machine-translating the speech recognized in the second language into speech, speech synthesis means for synthesizing speech into the second language machine-translated by the machine translation means, and speech input in the first language. Voice output control means for controlling to output a voice of the speaker and the voice of the second language from the machine translation means in a predetermined order; and a voice output from the voice output control means. Communication means for communicating with the utterance partner.

The communication method according to the present invention recognizes a speaker's voice input in a first language, machine-translates the recognized voice into a second language, and performs the machine-translated second A voice is synthesized with a language, and a voice of the speaker input in the first language and a voice of the second language are output in a predetermined order, and the voice output in the predetermined order is output from the speaker. The communication is made to the utterance partner of the utterance.

The recording medium storing the communication control program according to the present invention recognizes a speaker's voice input in a first language, and machine-translates the recognized voice into a second language. Synthesizing the speech into the translated second language, outputting the speech of the speaker input in the first language and the speech of the second language from the machine translation means in a predetermined order,
A communication control program for communicating the voice output in the predetermined order to the utterer of the utterer is recorded.

[0010] A communication device according to the present invention is a speech recognition means for recognizing a speech of a speaker input in a first language, and a machine for machine-translating the speech recognized by the speech recognition means into a second language. Translation means; speech synthesis means for synthesizing speech into the second language machine-translated by the machine translation means;
And a communication unit for communicating the voice output from the synthesizing unit to the speaker and the other party of the speaker.

The communication method according to the present invention recognizes a voice of a speaker input in a first language, and machine-translates the recognized voice into a second language. A voice is synthesized with a language, and the synthesized voice is communicated to the speaker and the utterance partner of the speaker.

A recording medium storing a communication control program according to the present invention recognizes a voice of a speaker input in a first language, and machine-translates the recognized voice into a second language. A communication control program for synthesizing speech into the translated second language and communicating the synthesized speech to the speaker and the utterer of the speaker is recorded.

[0013]

Embodiments of the present invention will be described below with reference to the drawings.

First, a first embodiment will be described. The present invention relates to a communication system 1 having a configuration shown in FIG.
Applied to The communication system 1 includes two communication devices 10 and 20 connected via a communication network.

The communication device 10 includes a speech recognition circuit 11 for recognizing a speech uttered by the user A, a machine translation circuit 12 for translating a certain language into another language, and a machine for converting the other language into speech. A speech synthesis circuit 13, a speech buffer circuit 14 for temporarily storing speech uttered by the user A, and a speech translation control circuit 15 for controlling output of translated speech and the like.

Further, the communication device 20 temporarily stores a voice recognition circuit 21 for recognizing a voice uttered by the user B, a machine translation circuit 22, a voice synthesis circuit 23, and a voice uttered by the user B. An utterance buffer circuit 24 and a speech translation control circuit 25 are provided. Since the communication device 20 has the same configuration as the communication device 10, a detailed description thereof will be omitted.

The voice recognition circuit 11 performs a frequency analysis of the voice signal using, for example, a general FFT as a frequency analysis method, and obtains a power spectrum of the voice signal which is a voice uttered by the user A. Then, a spectrum of the noise section is obtained by using a signal section other than the speech section as a noise section, and a process of subtracting the noise spectrum in the speech section is performed. Further, if the power spectrum of the result of the frequency analysis is used as it is, since the dimensions of the parameters are large, the feature amount of the voice signal spoken by the user A is extracted by performing compression processing to an appropriate dimension. A model (HMM: Hidden Markov) stored in a memory (not shown) in advance
Model A), the input speech of the user A is recognized and supplied to the machine translation circuit 12.

The machine translation circuit 12 translates the language of the speech recognized by the speech recognition circuit 11 into another language that can be heard by the user B.

The speech synthesis circuit 13 converts the translated other language into speech and supplies it to the speech translation control unit 15.

On the other hand, the voice spoken by the user A is stored in the speech buffer 14. The voice translation circuit 15 reads out the voice stored in the utterance buffer 14 at a predetermined timing, arranges the voice of the user A and the translated voice in a predetermined order, and sends these voices to the user B. Send.

It should be noted that the speech translation control circuit 15
The voice of the user A is read from the utterance buffer 14 in accordance with the output order of the uttered contents and the timing at which the translated voice is supplied from the voice synthesis circuit 13. Thereby, the speech translation control circuit 15
The content uttered by the user A can be supplied to the user B before or after the translated voice.

As described above, by transmitting the untranslated voice to the utterance partner in addition to the translated voice, the communication device 10 includes not only the translated voice but also the utterance of the user A. Intentions and emotions that have been sent can also be transmitted to the user B.

The communication device 10 may return the voice uttered by the user A and the translated voice to the user A itself. This prevents the user A from speaking at an erroneous timing even when the translation takes time.

Similarly, the communication device 20 can transmit to the user A not only the translated voice but also the intonation and the emotion included in the utterance of the user B.

Furthermore, the above-described communication device 10 may be mounted on a so-called communication terminal, or may be mounted on an exchange in a communication path.

Next, a second embodiment of the present invention will be described. In the second embodiment, as shown in FIG. 2, a reproduction buffer 30 is provided between the communication devices 10 and 20 shown in the first embodiment.

The reproduction buffer 30 may be provided in either the communication device 10 or the communication device 20.
It may be provided in a repeater (not shown) in a communication path between the communication devices 10 and 20.

The reproduction buffer 30 temporarily stores the voice from the voice translation control circuit 15 of the communication device 10, reproduces the voice and supplies the voice to the users A and B, and the voice of the communication device 20. The voice from the translation control circuit 25 is also temporarily stored, and the voice is reproduced to be used by the users A and B.
To supply.

Further, the reproduction buffer 30 may reproduce the voice of the speaker prior to the translated voice or after the translated voice.

As described above, since the communication device 10 allows both the user A and the user B to hear the same voice at the same time, even if the translation process takes a long time, for example, In addition, it is possible to prevent the other user from inadvertently starting talking while one user is listening to the translation result.

The contents described in the first and second embodiments may be carried out by installing the control program from a recording medium on which a control program for performing the above-described processing is recorded in a computer.

[0032]

As described above in detail, according to the communication device, the communication method, and the recording medium on which the communication control program is recorded according to the present invention, the voice of the speaker input in the first language is recognized. Machine-translated into a second language, synthesizes speech into the machine-translated second language, and outputs the speaker's speech input in the first language and the speech in the second language in a predetermined order Then, by communicating with the speaker, the intonation, emotion, and the like included in the speaker's speech can be transmitted to the speaker.

According to the communication device, the communication method, and the recording medium storing the communication control program according to the present invention, the voice of the speaker input in the first language is recognized, and the recognized voice is converted into the second language. Machine translation into a second language that has been machine translated, and synthesizing the synthesized speech to the speaker and the utterer of the speaker. In addition, it is possible to prevent one of the speakers from inadvertently starting to speak before the translation is completed.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of a communication device in a communication system to which the present invention has been applied.

FIG. 2 is a block diagram showing a configuration of another communication device to which the present invention is applied.

[Explanation of symbols]

1 communication system, 10,20 communication device, 11,21
Speech recognition circuit, 12, 22 Machine translation circuit, 13, 2
3 voice synthesis circuit, 14, 24 utterance buffer, 15,
25 speech translation control circuit, 30 playback buffer

Continued on the front page (72) Inventor Masato Shimakawa 6-35-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Inside Sony Corporation (72) Inventor Osamu Hamada 6-35-35 Kita-Shinagawa, Shinagawa-ku, Tokyo Sony Corporation In-house F term (reference) 5B091 AA03 CB12 CB32 CD13 5D015 AA05 KK04 5D045 AA07 AB03 5K034 AA18 BB06 CC05 DD01 EE12 FF17 FF20 HH01 HH02 HH13 HH16 HH17 HH62 MM18

Claims (24)

[Claims] 1. A speech recognition means for recognizing a speech of a speaker input in a first language, a machine translation means for machine-translating the speech recognized by the speech recognition means into a second language, and the machine A voice synthesizer for synthesizing a voice into a second language machine-translated by the translator; a voice of a speaker input in the first language and a voice of the second language from the voice synthesizer being predetermined And a communication unit for communicating the voice output from the voice output control unit to the utterer of the speaker. 2. A storage device for storing a voice of a speaker input in the first language, wherein the voice output control device includes a voice of the speaker in a first language stored in the storage device. Second from the above machine translation means
2. The communication device according to claim 1, wherein control is performed to output voices of the language in a predetermined order. 3. The communication apparatus according to claim 2, wherein said communication means communicates the voice output from said voice output control means to said speaker and said speaker. 4. Recognizing a speaker's voice input in a first language, machine-translating the recognized voice into a second language, and synthesizing voice into the machine-translated second language. Outputting the voice of the speaker input in the first language and the voice of the second language in a predetermined order, and communicating the voice output in the predetermined order to the utterer of the speaker; A communication method, comprising: 5. The speaker's voice input in the first language is stored in storage means, and the speaker's first language voice stored in the storage means and the machine-translated second voice are stored. 5. The communication method according to claim 4, wherein control is performed to output the voice of the language in a predetermined order, and the voice output in the predetermined order is communicated to a speech partner of the speaker. 6. The communication method according to claim 5, wherein the voice output in the predetermined order is communicated to the speaker and the other party. 7. Recognizing a speaker's voice input in a first language, machine-translating the recognized voice into a second language, and synthesizing voice into the machine-translated second language. Outputting the voice of the speaker input in the first language and the voice of the second language machine-translated in a predetermined order, and outputting the voice output in the predetermined order to the utterance of the speaker. A recording medium on which a communication control program for communicating with a partner is recorded. 8. The speaker's voice input in the first language is stored in storage means, and the speaker's first language voice stored in the storage means and the machine-translated second voice are stored. 8. The communication control program according to claim 7, wherein control is performed to output the voice of the language in a predetermined order, and the voice output in the predetermined order is communicated to a speech partner of the speaker. recoding media. 9. The recording medium according to claim 8, wherein said voice output in said predetermined order is communicated to said speaker and said speaker. 10. A speech recognition means for recognizing a speech of a speaker input in a first language, a machine translation means for machine-translating the speech recognized by the speech recognition means into a second language, and the machine A communication apparatus comprising: a voice synthesizing unit configured to synthesize a voice into a second language machine-translated by a translating unit; and a communication unit configured to communicate the voice output from the synthesizing unit to the speaker and the utterance partner of the speaker. . 11. A first storage means for storing a voice input in the first language, a second language from the first language voice stored in the first storage means and a second voice from the synthesis means. The communication device according to claim 10, further comprising: output control means for performing control to output a language voice in a predetermined order. 12. The communication apparatus according to claim 11, wherein the communication means communicates the voice output in the predetermined order to the speaker and the other party of the speaker. 13. The communication means has a second storage means for storing the voice from the voice synthesis means, and stores the voice stored in the second storage means in a predetermined order with the speaker and the speaker. The communication device according to claim 10, wherein the communication device communicates with the utterance partner. 14. A third storage means for storing a voice input in the first language, a second language from the first language voice stored in the third storage means and a second voice from the voice synthesis means. Output control means for performing control to output the voice of the language in a predetermined order, and the communication means writes the voice output in a predetermined order by the output control means in the third storage means, 14. The communication device according to claim 13, wherein the voice stored in the third storage unit is communicated to the speaker and the other party in a predetermined order. 15. Recognizing a voice of a speaker input in a first language, machine-translating the recognized voice into a second language, and synthesizing voice into the machine-translated second language. A communication method comprising: communicating the synthesized voice to the speaker and the utterer of the speaker. 16. A voice input in the first language is stored in a first storage means, and a voice in a first language and a voice in the second language stored in the first storage means are stored in the first storage means. 16. The communication method according to claim 15, wherein control is performed to output in a predetermined order. 17. The communication method according to claim 16, wherein the voice output in the predetermined order is communicated to the speaker and the utterer of the speaker. 18. A speech in a second language in which the speech is synthesized is stored in a second storage means, and the speeches stored in the second storage means are stored in a predetermined order in the speaker and the utterance thereof. The communication method according to claim 15, wherein the communication is performed with a partner. 19. The speech input in the first language is stored in a third storage means, and the speech in the first language stored in the third storage means and the synthesized second language are stored. Are output in a predetermined order, the sounds output in the predetermined order are stored in the second storage means, and the voices stored in the second storage means are output in a predetermined order. 19. The communication method according to claim 18, wherein the communication is performed with a person and his / her utterance partner. 20. Recognizing a speaker's voice input in a first language, machine-translating the recognized voice into a second language, and synthesizing voice into the machine-translated second language. A recording medium storing a communication control program for communicating the synthesized voice to the speaker and the utterer of the speaker. 21. A voice input in the first language is stored in a first storage means, and a voice in a first language and a voice in the second language stored in the first storage means are stored in the first storage means. 21. A control for outputting the data in a predetermined order.
A recording medium on which the communication control program described above is recorded. 22. The recording medium according to claim 21, wherein the voice output in the predetermined order is communicated to the speaker and the speaker of the speaker. 23. A second language voice synthesized with the voice is stored in a second storage means, and the voices stored in the second storage means are stored in a predetermined order in the speaker and the utterance thereof. 21. A recording medium recording a communication control program according to claim 20, wherein the communication medium communicates with a partner. 24. A voice input in the first language is stored in a third storage means, and the voice of the first language stored in the third storage means and the synthesized second language are stored. Are output in a predetermined order, the sounds output in the predetermined order are stored in the second storage means, and the voices stored in the second storage means are output in a predetermined order. 24. A recording medium storing a communication control program according to claim 23, wherein the communication medium communicates with a person and his / her utterance partner.